Skip to main content

Includes 694 hourly rounds up to 2026-11-16 from NIMStats by Mauro Druwel (source), measured with a different prompt and timeout. Our own probe adds a round every 30 minutes.

z

glm-5.3-flash

Unstable

Rank 12 of 15 Last probed (22 min ago)

z-ai/glm-5.3-flash answered 75.9% of probes on the NVIDIA NIM free API in the last 7 days, with a median time to first token of 185.7 s and 1.4 tok/s. It ranks 12 of 15 tracked models.

75.9% Uptime 120/158 probes
47/ 100 Score 3 round wins
185.7 s First token p95 295.9 s
191.6 s Full reply median
3.71 s Best reply fastest in range
1.4tok/s Throughput median

Model vs. median

Against the median of models that answered, last 7 days.

Uptime
75.9% 74.7%
1 pts above median
First token
185.7 s 14.8 s
13× worse than median
Full reply
191.6 s 22.6 s
8.5× worse than median
Throughput
1.4 tok/s 22.3 tok/s
16× worse than median

glm-5.3-flash median of answering models

Error breakdown

38 failed of 158 probes, last 7 days.

FailureProbesShare of failures
Timed out32 84.2%
Not served (404)4 10.5%
Network error1 2.6%
Server error (5xx)1 2.6%

Time to first token

Each probe. Lower is better.

0 ms125.0 s250.0 s375.0 s500.0 s11-10 17:0011-17 16:13 UTC
answered no answer

Throughput

Tokens per second after the first token, each probe. Higher is better.

0.0 tok/s25.0 tok/s50.0 tok/s75.0 tok/s100 tok/s11-10 17:0011-17 16:13 UTC
answered no answer

Availability heatmap

Last 7 days by UTC hour.

all answered some failed none answered not probed

Run history

Last 20 probes.

TimeResultFirst tokenFull replySpeed
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
Timed outn/an/an/a
OK294.0 s297.3 s0.8 tok/s
OK289.3 s296.0 s0.8 tok/s
Timed outn/an/an/a
OK290.5 s294.4 s0.8 tok/s
OK127.9 s129.9 s1.8 tok/s
OK165.9 s172.8 s1.4 tok/s
OK89.6 s97.7 s2.7 tok/s
OK251.8 s255.6 s0.9 tok/s

Call glm-5.3-flash

The endpoint is OpenAI-compatible.

Create a free key at build.nvidia.com, then:

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Authorization: Bearer $NVIDIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5.3-flash",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 256,
    "stream": true
  }'

Other models answering

Top of the leaderboard right now.